mlsanityData to 7 Oct 2026

INSID3: Training-Free In-Context Segmentation with DINOv3

arXiv 2603.28480 ↗First posted 30 Mar 2026cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

In-context segmentation (ICS) aims to segment arbitrary concepts, e.g., objects, parts, or personalized instances, given one annotated visual examples. Existing work relies on (i) fine-tuning vision foundation models (VFMs), which improves in-domain results but harms generalization, or (ii) combines multiple frozen VFMs, which preserves generalization but yields architectural complexity and fixed segmentation granularities. We revisit ICS from a minimalist perspective and ask: Can a single self-supervised backbone support both semantic matching and segmentation, without any supervision or auxiliary models? We show that scaled-up dense self-supervised features from DINOv3 exhibit strong spatial structure and semantic correspondence. We introduce INSID3, a training-free approach that segments concepts at varying granularities only from frozen DINOv3 features, given an in-context example. INSID3 achieves state-of-the-art results across one-shot semantic, part, and personalized segmentation, outperforming previous work by +7.5 % mIoU, while using 3x fewer parameters and without any mask or category-level supervision. Code is available at https://github.com/visinf/INSID3 .

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 66 of its 81 references that are in the map. First posted on arXiv 30 Mar 2026.

Builds on

66 of 81 references.

References · 66

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2022Training language models to follow instructions with human feedbackcited by 15,712
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  6. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  7. 2023Segment Anythingcited by 8,158
  8. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  9. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  10. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  11. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  12. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
38 more
  1. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  2. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  3. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  4. 2025DINOv3cited by 1,297
  5. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,062
  6. 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,020
  7. 2021iBOT: Image BERT Pre-Training with Online Tokenizercited by 891
  8. 2025SAM 3: Segment Anything with Conceptscited by 835
  9. 2019Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)cited by 657
  10. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  11. 2023Emergent Correspondence from Image Diffusioncited by 437
  12. 2022Images Speak in Images: A Generalist Painter for In-Context Visual Learningcited by 317
  13. 2025Perception Encoder: The best visual embeddings are not at the output of the networkcited by 315
  14. 2023A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondencecited by 297
  15. 2023Personalize Segment Anything Model with One Shotcited by 250
  16. 2022Unsupervised Semantic Segmentation by Distilling Feature Correspondencescited by 241
  17. 2020Space-Time Correspondence as a Contrastive Random Walkcited by 239
  18. 2023EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervisioncited by 216
  19. 2020How Well Do Self-Supervised Models Transfer?cited by 213
  20. 2023A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trendscited by 205
  21. 2021Unsupervised Semantic Segmentation by Contrasting Object Mask Proposalscited by 190
  22. 2019Feature Weighting and Boosting for Few-Shot Segmentationcited by 189
  23. 2017Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Artcited by 182
  24. 2023AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into Onecited by 165
  25. 2020Medical Image Segmentation Using Deep Learning: A Surveycited by 163
  26. 2021Efficient Visual Pretraining with Contrastive Detectioncited by 150
  27. 2022Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localizationcited by 150
  28. 2020Unsupervised Learning of Dense Visual Representationscited by 147
  29. 2023Matcher: Segment Anything with One Shot Using All-Purpose Feature Matchingcited by 142
  30. 2019SPair-71k: A Large-scale Benchmark for Semantic Correspondencecited by 140
  31. 2022Learning What Not to Segment: A New Perspective on Few-Shot Segmentationcited by 120
  32. 2022VICRegL: Self-Supervised Learning of Local Visual Featurescited by 118
  33. 2022Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentationcited by 114
  34. 2024FeatUp: A Model-Agnostic Framework for Features at Any Resolutioncited by 114
  35. 2021Instance Localization for Self-supervised Detection Pretrainingcited by 99
  36. 2020Semantic Segmentation of Underwater Imagery: Dataset and Benchmarkcited by 95
  37. 2023CLIP-DINOiser: Teaching CLIP a few DINO tricks for open-vocabulary semantic segmentationcited by 94
  38. 2024RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Modelscited by 88

50 most cited of 66 All 66 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 12.

12 papers.

  1. 2026Preserve, Then Resolve: Many-to-Many Association and Robust Estimation with General-Purpose Visual Featurescited by 0
  2. 2026Example-Based Object Detectioncited by 0
  3. 2026FROST: Training-Free Few-Shot Segmentation with Frozen Features and Nonparametric Statisticscited by 0
  4. 2026VocaDet: Sample-Driven Open-Vocabulary Object Detection and Segmentation via Visual Tokenization and Vector Database Retrievalcited by 0
  5. 2026REBASE: Reference-Background Subspace Elimination for Training-Free In-Context Segmentationcited by 0
  6. 2026SADe: Sparse-Atom Support Decontamination for Few-Shot Segmentation with Weak Support Annotationscited by 0
  7. 2026PATE-Forensics: Perception-as-Tool for Explainable Deepfake Forensics with General-Purpose MLLMscited by 0
  8. 2026Exemplar: Classical Priors Complement Frozen Features for Few-Shot Microscopy Segmentation at Native Resolutioncited by 0
  9. 2026FoRIS: Progressive Foreground Refinement for Training-Free In-Context Segmentationcited by 0
  10. 2026SegBanana: Steering Unified Multimodal Models into Medical Segmenterscited by 0
  11. 2026Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answeringcited by 0
  12. 2026One-Shot Adaptive Segmentation For Scientific Imagescited by 0